Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 218 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1180. Min Range: -4.1180
Max Act: 4.1180. Min Act: -0.1700
Data Index: 6420617 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.9929. Min Act: -0.1700
Data Index: 2055890 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.9617. Min Act: -0.1700
Data Index: 996486 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.9304. Min Act: -0.1700
Data Index: 2300691 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.9304. Min Act: -0.1700
Data Index: 2454083 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8991. Min Act: -0.1700
Data Index: 1871931 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8991. Min Act: -0.1700
Data Index: 643623 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8991. Min Act: -0.1700
Data Index: 2067417 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8991. Min Act: -0.1700
Data Index: 637148 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8679. Min Act: -0.1700
Data Index: 377848 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8991. Min Act: -0.1700
Data Index: 1927754 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8679. Min Act: -0.1700
Data Index: 8097802 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8679. Min Act: -0.1700
Data Index: 4414017 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8053. Min Act: -0.1700
Data Index: 6230908 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8679. Min Act: -0.1700
Data Index: 3426375 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8366. Min Act: -0.1700
Data Index: 3547128 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8053. Min Act: -0.1700
Data Index: 6050490 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8053. Min Act: -0.1700
Data Index: 5318128 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.8053. Min Act: -0.1700
Data Index: 1777706 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1180. Min Range: -4.1180
Max Act: 3.7741. Min Act: -0.1700
Data Index: 1564261 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19